diff --git a/README.md b/README.md index 77242d04f47168ca488fc3373eadfe227954f937..fb4e9b636d451222729d39bf6e195a2368314299 100644 --- a/README.md +++ b/README.md @@ -97,14 +97,14 @@ - [安装说明](docs/tutorials/INSTALL_cn.md) - [快速开始](docs/tutorials/QUICK_STARTED_cn.md) - [训练/评估/预测流程](docs/tutorials/GETTING_STARTED_cn.md) -- [常见问题汇总](docs/tutorials/FAQ.md) +- [常见问题汇总](docs/FAQ.md) ### 进阶教程 - [数据预处理及自定义数据集](docs/advanced_tutorials/READER.md) - [搭建模型步骤](docs/advanced_tutorials/MODEL_TECHNICAL.md) -- 模型参数配置: - - [配置模块设计和介绍](docs/advanced_tutorials/CONFIG_cn.md) - - [RCNN模型参数说明](docs/advanced_tutorials/RCNN_PARAMS_DOC.md) +- [模型参数配置](docs/advanced_tutorials/config_doc): + - [配置模块设计和介绍](docs/advanced_tutorials/config_doc/CONFIG_cn.md) + - [RCNN模型参数说明](docs/advanced_tutorials/config_doc/RCNN_PARAMS_DOC.md) - [迁移学习教程](docs/advanced_tutorials/TRANSFER_LEARNING_cn.md) - [IPython Notebook demo](demo/mask_rcnn_demo.ipynb) - [模型压缩](slim) diff --git a/README_en.md b/README_en.md index 76e347d23ba3e6ff74ecd115eed4b8fd67fd4590..0ebd054e8b417a9a90266523be09596fdd542d71 100644 --- a/README_en.md +++ b/README_en.md @@ -111,16 +111,16 @@ The following is the relationship between COCO mAP and FPS on Tesla V100 of repr - [Installation guide](docs/tutorials/INSTALL.md) - [Quick start on small dataset](docs/tutorials/QUICK_STARTED.md) - [Train/Evaluation/Inference](docs/tutorials/GETTING_STARTED.md) -- [FAQ](docs/tutorials/FAQ.md) +- [FAQ](docs/FAQ.md) ### Advanced Tutorial - [Guide to preprocess pipeline and custom dataset](docs/advanced_tutorials/READER.md) - [Models technical](docs/advanced_tutorials/MODEL_TECHNICAL.md) - [Transfer learning document](docs/advanced_tutorials/TRANSFER_LEARNING.md) -- Parameter configuration: - - [Introduction to the configuration workflow](docs/advanced_tutorials/CONFIG.md) - - [Parameter configuration for RCNN model](docs/advanced_tutorials/RCNN_PARAMS_DOC.md) +- [Parameter configuration](docs/advanced_tutorials/config_doc): + - [Introduction to the configuration workflow](docs/advanced_tutorials/config_doc/CONFIG.md) + - [Parameter configuration for RCNN model](docs/advanced_tutorials/config_doc/RCNN_PARAMS_DOC.md) - [IPython Notebook demo](demo/mask_rcnn_demo.ipynb) - [Model compression](slim) - [Model compression benchmark](slim) @@ -152,7 +152,7 @@ The following is the relationship between COCO mAP and FPS on Tesla V100 of repr PaddleDetection is released under the [Apache 2.0 license](LICENSE). ## Updates -v0.3.0 was released at `05/2020`, add anchor-free, EfficientDet, YOLOv4, etc. Launched mobile and server-side practical and efficient multiple models, refactored predictive deployment functions, and improved ease of use, fix many known bugs, etc. +v0.3.0 was released at `05/2020`, add anchor-free, EfficientDet, YOLOv4, etc. Launched mobile and server-side practical and efficient multiple models. For example, the YOLOv3-MobileNetv3 mobile side model is accelerated 3.5 times, the server side has optimized the two-stage model, and the speed and accuracy have high cost performance. We also refactored predictive deployment functions, and improved ease of use, fix many known bugs, etc. Please refer to [版本更新文档](docs/CHANGELOG.md) for details. ## Contributing diff --git a/demo/dropblock.png b/demo/dropblock.png deleted file mode 100644 index 66b8a88e39ad23f3e83ba7a49b93ebfdfcf5aacb..0000000000000000000000000000000000000000 Binary files a/demo/dropblock.png and /dev/null differ diff --git a/docs/advanced_tutorials/MODEL_TECHNICAL.md b/docs/advanced_tutorials/MODEL_TECHNICAL.md index 70bccb029d94e9e798bfb78215441aded0e3cdda..94bc71f27dcfca942c725c35d26fe1e3e653fc63 100644 --- a/docs/advanced_tutorials/MODEL_TECHNICAL.md +++ b/docs/advanced_tutorials/MODEL_TECHNICAL.md @@ -69,7 +69,7 @@ from .darknet import * **几点说明：** - 为了在yaml配置文件中灵活配置网络，所有Backbone、模型组件与architecture类需要利用`ppdet.core.workspace`里的`register`进行注册，形式请参考如上示例； - 在Backbone中都需定义`__init__`函数与`__call__`函数，`__init__`函数负责初始化参数，在调用此Backbone时会执行`__call__`函数； -- `__shared__`为了实现一些参数的配置全局共享，具体细节请参考[配置文件说明文档](CONFIG_cn.md#faq)。 +- `__shared__`为了实现一些参数的配置全局共享，具体细节请参考[配置文件说明文档](config_doc/CONFIG_cn.md#faq)。 2.配置编写： 在yaml文件中以注册好了的`DarkNet`类名为标题，可选择性的对`__init__`函数中的参数进行更新，不在配置文件中配置的参数会保持`__init__`函数中的初始化值： diff --git a/docs/advanced_tutorials/CONFIG.md b/docs/advanced_tutorials/config_doc/CONFIG.md similarity index 100% rename from docs/advanced_tutorials/CONFIG.md rename to docs/advanced_tutorials/config_doc/CONFIG.md diff --git a/docs/advanced_tutorials/CONFIG_cn.md b/docs/advanced_tutorials/config_doc/CONFIG_cn.md similarity index 100% rename from docs/advanced_tutorials/CONFIG_cn.md rename to docs/advanced_tutorials/config_doc/CONFIG_cn.md diff --git a/docs/advanced_tutorials/RCNN_PARAMS_DOC.md b/docs/advanced_tutorials/config_doc/RCNN_PARAMS_DOC.md similarity index 100% rename from docs/advanced_tutorials/RCNN_PARAMS_DOC.md rename to docs/advanced_tutorials/config_doc/RCNN_PARAMS_DOC.md diff --git a/docs/advanced_tutorials/config_doc/index.rst b/docs/advanced_tutorials/config_doc/index.rst new file mode 100644 index 0000000000000000000000000000000000000000..3e07a6af0cd2da8191601049c6941e6b7a9cb94e --- /dev/null +++ b/docs/advanced_tutorials/config_doc/index.rst @@ -0,0 +1,10 @@ +模型参数配置教程 +=========================================== + +.. toctree:: + :maxdepth: 2 + + CONFIG_cn.md + RCNN_PARAMS_DOC.md + +.. note:: 文中超链接以GitHub中展示为准，如出现超链接无法访问，请点击网页右上角「Edit on github」查看源文件进行索引，有任何问题欢迎在 `GitHub `_ 上提issue。 diff --git a/docs/advanced_tutorials/index.rst b/docs/advanced_tutorials/index.rst index 95c215f5cfc40b3271b67735c5313c5df4703f49..52f71be6a22d9ff5aee1cd133e1d2aec6c70053b 100644 --- a/docs/advanced_tutorials/index.rst +++ b/docs/advanced_tutorials/index.rst @@ -5,9 +5,9 @@ :maxdepth: 2 deploy/index + config_doc/index READER.md MODEL_TECHNICAL.md - CONFIG_cn.md TRANSFER_LEARNING_cn.md slim/index diff --git a/docs/tutorials/GETTING_STARTED.md b/docs/tutorials/GETTING_STARTED.md index 405f1eb0e09c0be1b577184df235b8a06ffdf0cd..1b509df0ed90c116357435965cef29657dedbf82 100644 --- a/docs/tutorials/GETTING_STARTED.md +++ b/docs/tutorials/GETTING_STARTED.md @@ -29,7 +29,7 @@ list below can be viewed by `--help` | FLAG | script supported | description | default | remark | | :----------------------: | :------------: | :---------------: | :--------------: | :-----------------: | -| -c | ALL | Select config file | None | **The description of configure can refer to [CONFIG.md](../advanced_tutorials/CONFIG.md)** | +| -c | ALL | Select config file | None | **The description of configure can refer to [CONFIG.md](../advanced_tutorials/config_doc/CONFIG.md)** | | -o | ALL | Set parameters in configure file | None | `-o` has higher priority to file configured by `-c`. Such as `-o use_gpu=False max_iter=10000` | | -r/--resume_checkpoint | train | Checkpoint path for resuming training | None | `-r output/faster_rcnn_r50_1x/10000` | | --eval | train | Whether to perform evaluation in training | False | | @@ -100,7 +100,7 @@ list below can be viewed by `--help` ##### NOTES -- `CUDA_VISIBLE_DEVICES` can specify different gpu numbers. Such as: `export CUDA_VISIBLE_DEVICES=0,1,2,3`. GPU calculation rules can refer [FAQ](./FAQ.md) +- `CUDA_VISIBLE_DEVICES` can specify different gpu numbers. Such as: `export CUDA_VISIBLE_DEVICES=0,1,2,3`. GPU calculation rules can refer [FAQ](../FAQ.md) - Dataset will be downloaded automatically and cached in `~/.cache/paddle/dataset` if not be found locally. - Pretrained model is downloaded automatically and cached in `~/.cache/paddle/weights`. - Checkpoints are saved in `output` by default, and can be revised from save_dir in configure files. diff --git a/docs/tutorials/GETTING_STARTED_cn.md b/docs/tutorials/GETTING_STARTED_cn.md index ea63d2567c43043b11a6d150edd3606d3d21e900..7f26016545d499f18df55dd5f81579cdd459302a 100644 --- a/docs/tutorials/GETTING_STARTED_cn.md +++ b/docs/tutorials/GETTING_STARTED_cn.md @@ -26,7 +26,7 @@ python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_img=demo/0000005 | FLAG | 支持脚本 | 用途 | 默认值 | 备注 | | :----------------------: | :------------: | :---------------: | :--------------: | :-----------------: | -| -c | ALL | 指定配置文件 | None | **配置模块说明请参考[配置模块](../advanced_tutorials/CONFIG_cn.md)** | +| -c | ALL | 指定配置文件 | None | **配置模块说明请参考[配置模块](../advanced_tutorials/config_doc/CONFIG_cn.md)** | | -o | ALL | 设置配置文件里的参数内容 | None | 使用-o配置相较于-c选择的配置文件具有更高的优先级。例如：`-o use_gpu=False max_iter=10000` | | -r/--resume_checkpoint | train | 从某一检查点恢复训练 | None | `-r output/faster_rcnn_r50_1x/10000` | | --eval | train | 是否边训练边测试 | False | | @@ -97,7 +97,7 @@ python tools/infer.py -c configs/faster_rcnn_r50_1x.yml --infer_img=demo/0000005 **提示:** -- `CUDA_VISIBLE_DEVICES` 参数可以指定不同的GPU。例如: `export CUDA_VISIBLE_DEVICES=0,1,2,3`. GPU计算规则可以参考 [FAQ](./FAQ.md) +- `CUDA_VISIBLE_DEVICES` 参数可以指定不同的GPU。例如: `export CUDA_VISIBLE_DEVICES=0,1,2,3`. GPU计算规则可以参考 [FAQ](../FAQ.md) - 若本地未找到数据集，将自动下载数据集并保存在`~/.cache/paddle/dataset`中。 - 预训练模型自动下载并保存在`〜/.cache/paddle/weights`中。 - 模型checkpoints默认保存在`output`中，可通过修改配置文件中save_dir进行配置。